Low-altitude UAV Environmental Monitoring and Pollution Early Warning System

Abstract

The present invention discloses a low-altitude drone environmental monitoring and pollution warning system. The present invention relates to the technical field of environmental monitoring, and solves the problem that drones cannot find the specific area corresponding to the anomaly based on the spatial characteristics of the points, resulting in insufficient accuracy of the original pollution warning. By analyzing the relevant data collected by the low-altitude drone, based on the analysis results, the spatial anomaly points are locked. Then, based on the positions of the spatial anomaly points, by constructing a spatial circle and a spherical area, the characteristic points with the highest pollution concentration are confirmed one by one, and the correlation confirmation is carried out step by step until the corresponding anomaly circle area is determined. By adopting this confirmation method, the area with the most serious pollution concentration can be quickly and effectively locked, and pollution warning can be carried out based on the determined area, which can ensure the specific accuracy of the pollution warning and achieve a better pollution concentration warning effect.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental monitoring, and specifically to a low-altitude unmanned aerial vehicle (UAV) environmental monitoring and pollution warning system. Background Art

[0002] By controlling a low-altitude UAV, the UAV is used to detect pollutant gases in the atmosphere, including but not limited to sulfur dioxide (SO 2 ), nitrogen oxides (NO x ), carbon monoxide (CO), ozone (O 3 ), and volatile organic compounds (VOCs), etc.; the concentration levels of these pollutants are crucial for evaluating air quality. For example, in an urban environment, through the gas sensors carried by a low-altitude UAV, the change in the concentration of NO x around a busy traffic intersection can be accurately monitored.

[0003] The application with the publication number CN106643916A discloses a UAV environmental monitoring system and a monitoring method. The UAV environmental monitoring system includes a flight control module, a navigation module, a data acquisition module, an environmental detection module, an optical camera, a barometric altimeter, a memory, a wireless transmission module installed on the UAV, and a ground workstation; the data acquisition module is connected to the environmental detection module, and the data acquisition module is also connected to the GPS and the barometric altimeter, and is also connected to the memory; the optical camera stores pictures in the memory; the wireless transmission module is connected to the ground workstation through a wireless communication network, and the ground workstation controls the UAV, and receives environmental data, geographical data, and picture data, and stores and analyzes and processes them. This monitoring system realizes the functions of rapid, comprehensive, and accurate monitoring of the environmental protection monitoring area, and improves the efficiency, real-time performance, and intuitiveness of the monitoring.

[0004] In the actual application process of its UAV environmental monitoring system, generally, the UAV is controlled to fly according to a preset flight route, and then based on the air data collected during the flight, the air pollution situation at relevant spatial points is analyzed, and early warnings are made based on the corresponding analysis results. However, the original method can only target the air data of the set collection points, and the pollution concentration of such collection points does not belong to the most serious area, and the UAV cannot find the specific area corresponding to the abnormality according to the spatial characteristics of the points. Therefore, the accuracy of the original pollution warning is not precise enough, and a better pollution warning effect cannot be achieved. Summary of the Invention

[0005] Aiming at the deficiencies of the prior art, the present invention provides a low-altitude UAV environmental monitoring and pollution warning system, which solves the problem that the UAV cannot find the specific area corresponding to the abnormality according to the spatial characteristics of the points, resulting in insufficient accuracy of the original pollution warning.

[0006] To achieve the above object, the present invention is realized through the following technical solutions: a low-altitude UAV environmental monitoring and pollution warning system, including:

[0007] A real-time UAV data analysis terminal, which analyzes the air data collected by the low-altitude UAV in real time, and based on the real-time analysis results, determines spatial abnormal points. The specific method is as follows:

[0008] Process the air data generated by the acquisition node in real time: check the corresponding acquisition items in the air data with the preset standard values, and calibrate the value of the corresponding acquisition item as S i , and calibrate the preset standard value of the corresponding acquisition item as B i , where i represents different acquisition items;

[0009] Adopt S i -B i =GX i Lock the associated value. If GX i ≤0, record the currently determined GX i as 0;

[0010] Assume i = 1, 2,..., n, where n represents the total number of acquisition items. Adopt YC i =GX 1 ×C1 + GX 2 ×C2 +... + GX n ×Cn to lock the abnormal value YC of the corresponding acquisition node i , where C1, C2,..., Cn are all preset factors associated with the corresponding acquisition items;

[0011] Compare the abnormal value YC i with the preset value Y1, where Y1 is the preset evaluation value. If YC i ≤Y1, no calibration is performed. If YC i >Y1, calibrate this acquisition node as a spatial abnormal point and transmit this spatial abnormal point to the abnormal point position positioning terminal;

[0012] An abnormal point position positioning terminal, which locks the spatial coordinate position of this spatial abnormal point in the preset three-dimensional space based on the confirmed spatial abnormal point. The specific method is as follows:

[0013] Based on the spatial coordinate positions of the determined spatial anomaly points, generate a set of spatial circles. These spatial circles are parallel to the horizontal plane of the three-dimensional space, and the spatial circles are preset circles with a preset internal radius. The spatial coordinate positions are the centers of the spatial circles. Control a low-altitude drone to collect air data of different spatial points within this spatial circle, and confirm the anomaly values corresponding to each different spatial point one by one. Select the maximum value from the confirmed several groups of anomaly values, and mark the spatial point corresponding to this maximum value as the first feature point;

[0014] Taking the first feature point as the center point, determine a set of spherical regions, and the spherical radius of the spherical region is a preset value. Control the low-altitude drone to collect and confirm the anomaly values of the air data of different spatial points within this spherical region. Lock the maximum value from the anomaly values corresponding to several different spatial points, and determine the second feature point;

[0015] Then, taking the second feature point as the center, construct a spatial circle again, and so on, confirm each subsequent feature point one by one. When the subsequent confirmed feature point is the same as the feature point confirmed in the previous set of confirmation processes, mark the circumferential region associated with the spatial circle where this feature point is located as the abnormal circumferential region within the region where this spatial anomaly point is located. After the abnormal circumferential region of this spatial anomaly point is confirmed, make the drone collect data according to the original flight route, and perform associated confirmation on subsequent spatial anomaly points and the corresponding abnormal circumferential regions;

[0016] And transmit the abnormal circumferential regions of several spatial anomaly points confirmed during this flight process to the cross-region integration processing end;

[0017] The circumferential control analysis end, based on the spatial coordinate positions of the locked spatial anomaly points, performs circumferential confirmation, and performs associated confirmation of feature points within the confirmed circumference. Based on the gradually confirmed feature points, lock the abnormal circumferential region within the region where this spatial anomaly point is located;

[0018] The cross-region integration processing end, based on several groups of abnormal circumferential regions confirmed during the flight of this low-altitude drone, associates and integrates the abnormal circumferential regions with the same spatial characteristics, and transmits the integrated set of circumferences with the same characteristics and the corresponding abnormal circumferential regions to the region analysis and early warning end:

[0019] Based on the confirmed several groups of abnormal circumferential regions, lock the specific position of the abnormal circumferential region in the three-dimensional space, and randomly move a single group of abnormal circumferential regions vertically up and down to evaluate whether there are other abnormal circumferential regions intersecting with the moved abnormal circumferential region. If they intersect, integrate the intersecting regions so that several groups of abnormal circumferential regions with intersections are combined into a set of circumferences with the same characteristics. If they do not intersect, do not perform any processing;

[0020] The regional analysis and early warning terminal comprehensively evaluates the abnormal values associated with the spatial points within the set of circular regions with the same characteristics or a single abnormal circular region based on the confirmed set of circular regions with the same characteristics or a single abnormal circular region, and determines whether to generate a regional early warning signal based on the evaluation result:

[0021] For the confirmed single abnormal circular region, confirm the abnormal values associated with several spatial points within this abnormal circular region, perform an average value process on the confirmed several groups of abnormal values, lock and check the average value. If the checked average value > Y2, generate a regional early warning signal for this abnormal circular region and display it through the display terminal, where Y2 is a preset value. If the checked average value ≤ Y2, no signal is generated, and directly display this abnormal circular region through the display terminal;

[0022] For the set of circular regions with the same characteristics, confirm the abnormal values associated with several spatial points of several abnormal circular regions within this set, perform an average value process on several groups of abnormal values, determine the checked average value. If the checked average value > Y2, generate a regional early warning signal for this set of circular regions with the same characteristics and display it through the display terminal, where Y2 is a preset value. If the checked average value ≤ Y2, no signal is generated, and directly display several abnormal circular regions within this set of circular regions with the same characteristics through the display terminal.

[0023] Preferably, the low-altitude unmanned aerial vehicle flies and collects data according to a preset flight route, and several equidistant collection nodes are preset synchronously within the flight route.

[0024] Preferably, different abnormal circular regions within the set of circular regions with the same characteristics all carry the same characteristic mark, and the characteristic mark is a preset mark, and different sets of circular regions with the same characteristics correspond to different characteristic marks.

[0025] The present invention provides a low-altitude unmanned aerial vehicle environmental monitoring and pollution early warning system. Compared with the prior art, it has the following beneficial effects:

[0026] The present invention analyzes the relevant data collected by the low-altitude unmanned aerial vehicle. Based on the analysis result, locks the spatial abnormal points, and then, based on the positions of the spatial abnormal points, by constructing spatial circles and spherical regions, confirms one by one the characteristic points with the highest pollution concentration, and gradually conducts associated confirmation backward until the corresponding abnormal circular region is determined. By adopting this confirmation method, the corresponding region with the most serious pollution concentration can be quickly and effectively locked, and pollution early warning is carried out based on the determined region, which can ensure the specific accuracy of pollution early warning and achieve a better pollution concentration early warning effect;

[0027] Subsequently, integrate the abnormal circle areas with similar spatial features, confirm their corresponding sets, and then comprehensively evaluate and give a comprehensive early warning for the numerical features of the relevant sets, which can avoid the duplication of pollution early warnings, improve the overall accuracy of its pollution early warning, and thus achieve a better pollution early warning effect. Brief Description of the Drawings

[0028] Figure 1 It is a schematic diagram of the principle framework of the present invention;

[0029] Figure 2 It is a schematic diagram for determining the abnormal circumferential area of the present invention. Detailed Embodiment

[0030] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0031] The First Embodiment

[0032] Please refer to Figure 1 , this application provides a low-altitude drone environmental monitoring and pollution early warning system, including a real-time drone data analysis terminal, an abnormal point positioning terminal, a circumferential control analysis terminal, an abnormal area integration and processing terminal, a regional analysis and early warning terminal, and a display terminal. Among them, the real-time drone data analysis terminal is electrically connected to the input nodes of the abnormal point positioning terminal or the circumferential control analysis terminal respectively, and the abnormal point positioning terminal, the circumferential control analysis terminal, the abnormal area integration and processing terminal, the regional analysis and early warning terminal, and the display terminal are electrically connected from the output node to the input node respectively;

[0033] Among them, the real-time drone data analysis terminal analyzes the air data collected by the low-altitude drone in real time. The low-altitude drone flies and collects data according to a preset flight route, and a number of equally spaced collection nodes are preset in the flight route. Based on the real-time analysis results, spatial abnormal points are determined and transmitted to the abnormal point positioning terminal. Specifically, when the low-altitude drone conducts environmental monitoring, it flies according to a preset flight route and stops at each different collection node. The collection nodes are preset in the flight route, and the air data of the collection nodes are collected and analyzed according to the set collection logic. The air data includes sulfur dioxide (SO 2 ) content, nitrogen oxides (NO x ) content, volatile organic compounds (VOCs) content, etc. The specific method for determining spatial abnormal points is as follows:

[0034] Process the air data generated in real time by the acquisition nodes: Compare the corresponding acquisition items in the air data with the preset standard values, and calibrate the value of the corresponding acquisition item as S i Calibrate the preset standard value of the corresponding acquisition item as B i where i represents different acquisition items, such as sulfur dioxide content, nitrogen oxide content, etc.;

[0035] Use S i -B i = GX i Lock the associated value. If GX i ≤ 0, mark the currently determined GX i as 0. For example, that is, when GX i is negative, in order not to affect its subsequent specific confirmation, mark this negative number as 0 to prevent affecting the subsequent overall value determination;

[0036] Assume i = 1, 2,..., n, where n represents the total number of acquisition items. Use YC i = GX 1 × C1 + GX 2 × C2 +... + GX n × Cn to lock the outlier YC of the corresponding acquisition node i where C1, C2,..., Cn are all preset factors associated with the corresponding acquisition items, which are determined in advance by the operator;

[0037] Compare the outlier YC i with the preset value Y1. Here, Y1 is the preset evaluation value, which is determined in advance by the operator. If YC i ≤ Y1, no calibration is performed. If YC i > Y1, mark this acquisition node as a spatial anomaly point and transmit this spatial anomaly point to the anomaly position positioning end;

[0038] Specifically, after the drone reaches the specified acquisition node, it will stay at the corresponding acquisition node to complete the air data acquisition process at the corresponding node. The air data includes several acquisition items, which respectively correspond to different air pollutant content data. Each content data has a corresponding evaluation standard. Based on the overall numerical analysis results of several air data and several evaluation standards, the corresponding outlier can be locked, and then the anomaly determination of the corresponding node can be performed based on the determined outlier.

[0039] Among them, the abnormal point positioning end locks the spatial coordinate point of this spatial abnormal point in the preset three-dimensional space based on the confirmed spatial abnormal point, and transmits the determined spatial coordinate point to the circumferential control analysis end. Specifically, the three-dimensional space is constructed in advance by the operator and is consistent with the area detected by the corresponding low-altitude unmanned aerial vehicle. The flight route of the low-altitude unmanned aerial vehicle can be reflected in this three-dimensional space, so that the corresponding spatial coordinate point can be determined based on the confirmed spatial abnormal point, thereby calibrating the spatial abnormal point;

[0040] The circumferential control analysis end performs circumferential confirmation based on the spatial coordinate point of the locked spatial abnormal point, and performs associated confirmation of characteristic points within the confirmed circumference. Based on the gradually confirmed characteristic points, the abnormal circumferential area within the area where this spatial abnormal point is located is locked. Specifically, in order to find a more accurate air pollution area, it is necessary to perform step-by-step analysis based on the determined spatial abnormal point. Here, the area confirmation method is used to confirm the air pollution conditions involved in different associated areas, and a more accurate abnormal circumferential area is locked from the confirmation results. Among them, the specific method for locking the abnormal circumferential area is as follows:

[0041] Based on the spatial coordinate point of the determined spatial abnormal point, a set of spatial circles is generated. This spatial circle is parallel to the horizontal plane of the three-dimensional space, and the spatial circle is a preset circle with a preset internal radius. The spatial coordinate point is the center of the spatial circle. Control the low-altitude unmanned aerial vehicle to collect air data of different spatial points within this spatial circle, and confirm each abnormal value corresponding to each different spatial point one by one. Select the maximum value from the confirmed groups of abnormal values, and calibrate the spatial point corresponding to this maximum value as the first characteristic point;

[0042] Taking the first characteristic point as the center point, determine a set of spherical areas, and the spherical radius of the spherical area is a preset value. Control the low-altitude unmanned aerial vehicle to collect and confirm the abnormal values of the air data of different spatial points within this spherical area. Lock the maximum value from the abnormal values corresponding to several different spatial points, and determine the second characteristic point;

[0043] Using the second feature point as the center, construct a spatial circle again, and so on, to confirm each subsequent feature point one by one. When the subsequent confirmed feature point is the same as the feature point confirmed in the previous group of confirmation processes (example: assume there is a feature point A. First, construct a corresponding spatial circle through A, lock the maximum value of the outliers within the spatial circle, and thus lock the corresponding feature point. If the feature point selected this time is still A, it means that the confirmed feature point has not changed at all. Similarly, if the feature point is A and the constructed area is a spherical area, within this spherical area, the confirmed feature point is also A. Then the feature point confirmed this time is the same as the feature point confirmed last time, that is, there is no change. Then the corresponding A is the point with the largest outlier value in the two confirmation processes before and after, and the currently confirmed area is the area with the highest degree of abnormality), mark the circumferential area associated with the spatial circle where this feature point is located as the abnormal circumferential area within the area where this spatial abnormal point is located. After the abnormal circumferential area of this spatial abnormal point is confirmed, make the drone collect data according to the original flight route, and perform associated confirmation on subsequent spatial abnormal points and their corresponding abnormal circumferential areas. Example: Combine Figure 2 , determine a corresponding set of spatial abnormal points in the three-dimensional space, lock the spatial circle regarding this point based on the confirmed spatial abnormal points, then analyze several spatial points inside the spatial circle, lock the corresponding first feature point, based on the confirmed first feature point, use the first feature point as the center, and construct a corresponding set of spherical areas. Then, and so on, confirm the second feature point again in the spherical area, and confirm the spatial circle of the second feature point, and stop when the subsequent sequentially confirmed feature points repeat. In this way of processing, based on the confirmed spatial abnormal points, the associated area with the highest degree of abnormality can be gradually analyzed and confirmed;

[0044] And transmit the abnormal circumferential areas of several spatial abnormal points confirmed during this flight process to the cross-region integration processing terminal;

[0045] Specifically, each different spatial abnormal point will confirm a set of abnormal circumferential areas. Therefore, during the actual flight collection and processing of the low-altitude drone, the spatial abnormal points can be confirmed one by one. After each set of spatial abnormal points is confirmed, the abnormal circumferential area associated with this spatial abnormal point is confirmed, and then the unfinished flight collection task is executed to confirm each subsequent different spatial abnormal point one by one. Until the flight ends, several sets of abnormal circumferential areas are obtained.

[0046] Second Embodiment

[0047] This embodiment is a further embodiment of the first embodiment, and its main execution terminal is the cross-region integration processing terminal, which is used to perform specific integration and analysis on the confirmed several sets of abnormal circumferential areas;

[0048] Among them, the cross-region integration processing end, based on several groups of abnormal circular regions confirmed during the flight of the low-altitude unmanned aircraft this time, associates and integrates the abnormal circular regions with the same spatial characteristics, and transmits the integrated circular region set with the same characteristics and the corresponding abnormal circular regions to the region analysis and early warning end. Among them, the specific method of association and integration is as follows:

[0049] Based on the confirmed several groups of abnormal circular regions, lock the specific positions of the abnormal circular regions in three-dimensional space, and randomly move a single group of abnormal circular regions vertically up and down to evaluate whether there are other abnormal circular regions intersecting with the moved abnormal circular regions. If they intersect, integrate the intersecting regions so that several groups of abnormal circular regions with intersections are combined into a circular region set with the same characteristics. If they do not intersect, no processing is performed;

[0050] Different abnormal circular regions within the circular set with the same characteristics are all marked with the same characteristic mark, and the characteristic mark is a preset mark, which is determined in advance by the operator, and different circular sets with the same characteristics correspond to different characteristic marks;

[0051] Specifically, for the confirmed abnormal circular regions with the same characteristics, it means that such regions are basically of different heights, but the covered spatial coverage is relatively the same. Therefore, they are basically produced by the same pollution source. Only due to the influence of the corresponding wind force, multiple different abnormal circular regions are confirmed, but the multiple different abnormal circular regions are relatively consistent in spatial characteristics.

[0052] The Third Embodiment

[0053] In the specific implementation process of this embodiment, it is a further embodiment of the above two groups of embodiments, and it mainly focuses on the abnormal analysis process of the abnormal circular regions, which is associated and executed by the region analysis and early warning end;

[0054] Among them, the region analysis and early warning end, based on the confirmed circular region set with the same characteristics or a single abnormal circular region, comprehensively evaluates the abnormal values associated with the spatial points within the circular region set with the same characteristics or a single abnormal circular region, and determines whether to generate a region early warning signal and display it through the display end based on the evaluation result. The specific sub-steps for comprehensively evaluating the associated abnormal values are as follows:

[0055] For the confirmed single abnormal circular region, confirm the abnormal values associated with several spatial points within this abnormal circular region, and perform mean processing on the confirmed several groups of abnormal values, lock and check the mean value. If the checked mean value > Y2, generate a region early warning signal for this abnormal circular region and display it through the display end, where Y2 is a preset value, and its specific value is determined by the operator according to experience. If the checked mean value ≤ Y2, no signal is generated, and directly display this abnormal circular region through the display end;

[0056] For the set of circumferential regions with the same characteristics, confirm the outliers associated with a number of spatial points in a number of abnormal circumferential regions within this set, perform mean processing on several groups of outliers to determine the verification mean. If the verification mean > Y2, generate a regional warning signal for this set of circumferential regions with the same characteristics and display it through the display terminal. If the verification mean ≤ Y2, do not generate any signal and directly display several abnormal circumferential regions within this set of circumferential regions with the same characteristics through the display terminal;

[0057] Specifically, when confirming the corresponding abnormal circumferential region, the outliers associated with each internal spatial point have been relatedly confirmed. Therefore, based on the corresponding confirmation process, the related verification mean can be locked. Subsequently, the corresponding pollution warning process can be completed by performing anomaly confirmation through the corresponding verification mean.

[0058] Some of the data in the above formula are numerically calculated after removing their dimensions, and the content not described in detail in this specification belongs to the prior art well-known to those skilled in the art.

[0059] The above embodiments are only used to illustrate the technical method of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. Low-altitude UAV environmental monitoring and pollution warning system, characterized by: include: The drone data real-time analysis terminal performs real-time analysis on the air data collected by low-altitude drones and determines spatial abnormal points based on the real-time analysis results; The abnormal point positioning terminal, based on the confirmed spatial abnormal point, locks the spatial coordinate point of this spatial abnormal point in the preset three-dimensional space. The specific method is as follows: Based on the spatial coordinate point of the determined spatial abnormal point, a group of spatial circles is generated, the spatial circle is parallel to the horizontal plane of the three-dimensional space, and the spatial circle is a preset circle, and its internal radius is a preset value. The spatial coordinate point is the center of the spatial circle, and the low-altitude drone is controlled to collect air data of different spatial points in the spatial circle, and the abnormal values ​​corresponding to each different spatial point are confirmed one by one, and the maximum value is selected from the confirmed groups of abnormal values, and the spatial point corresponding to the maximum value is marked as the first feature point; Taking the first characteristic point as the center point, a group of spherical areas are determined, and the spherical radius of the spherical area is a preset value, and the low-altitude drone is controlled to collect air data of different spatial points in the spherical area and confirm the abnormal values, and the maximum value is locked from the abnormal values ​​corresponding to several different spatial points, and the second characteristic point is determined; Then, the second feature point is used as the center of the circle to construct a space circle again. Similarly, the subsequent feature points are confirmed one by one. When the feature points confirmed subsequently are consistent with the feature points confirmed in the previous set of confirmation processes, the circumference area associated with the space circle where the feature point is located is marked as the abnormal circumference area within the area where the spatial abnormal point is located. After the abnormal circumference area of ​​the spatial abnormal point is confirmed, the drone is made to collect data according to the original flight route, and the subsequent spatial abnormal points and the corresponding abnormal circumference areas are associated and confirmed; The abnormal circular areas of several spatial abnormal points confirmed during this flight are transmitted to the different-area integration processing terminal; The circumference control analysis end performs circumference confirmation based on the spatial coordinate points of the locked spatial abnormal point, and performs associated confirmation of the characteristic points within the confirmed circumference. Based on the gradually confirmed characteristic points, the abnormal circumference area within the area where the spatial abnormal point is located is locked; The heterogeneous area integration processing end associates and integrates the abnormal circular areas with the same spatial characteristics based on the several groups of abnormal circular areas confirmed during the flight of the low-altitude UAV, and transmits the integrated set of circular areas with the same characteristics and the corresponding abnormal circular areas to the regional analysis and warning end; The regional analysis and warning end, based on the confirmed set of circular areas with the same characteristics or a single abnormal circular area, comprehensively evaluates the abnormal values ​​associated with the spatial points in the set of circular areas with the same characteristics or a single abnormal circular area, and determines whether to generate a regional warning signal based on the evaluation results.

2. The low-altitude UAV environment monitoring and pollution early warning system according to claim 1 is characterized in that: The low-altitude UAV performs flight collection according to a preset flight route, and a plurality of equidistant collection nodes are synchronously preset in the flight route.

3. The low-altitude UAV environment monitoring and pollution early warning system according to claim 2 is characterized in that: The specific method of determining the spatial abnormal point by the drone data real-time analysis terminal is as follows: Process the air data generated by the collection node in real time: check the corresponding collection items in the air data with the preset standard values, and calibrate the values ​​of the corresponding collection items as S i , calibrate the preset standard value of the corresponding collection item as B i , where i represents different collection items; Using S i -B i =GX i Lock the associated value. If GX i ≤0, the currently determined GX i Recorded as 0; It is proposed that i=1, 2, ..., n, where n represents the total number of collection items, and YC i =GX1×C1+GX2×C2+……+GX n ×Cn locks the abnormal value YC of the corresponding acquisition node i , where C1, C2, ..., Cn are preset factors associated with the corresponding collection items; The outlier YC i Verify with the preset value Y1, where Y1 is the preset evaluation value. i ≤Y1, no calibration is performed. If YC i >Y1, mark this acquisition node as a spatial anomaly point, and transmit this spatial anomaly point to the anomaly point positioning terminal.

4. The low-altitude UAV environment monitoring and pollution early warning system according to claim 1 is characterized in that: The specific method of associating and integrating the abnormal circular areas with the same spatial characteristics at the heterogeneous area integration processing end is as follows: Based on the confirmed groups of abnormal circular areas, the specific positions of the abnormal circular areas are locked in three-dimensional space, and a single group of abnormal circular areas is randomly moved vertically up and down to assess whether there are other abnormal circular areas intersecting with the moved abnormal circular areas. If so, the intersecting areas are integrated so that the intersecting groups of abnormal circular areas are merged into a set of circular areas with the same characteristics. If not, no processing is performed.

5. The low-altitude UAV environment monitoring and pollution early warning system according to claim 4 is characterized in that: Different abnormal circular areas within the same characteristic circular set all carry the same characteristic mark, and the characteristic mark is a preset mark, and different same characteristic circular sets correspond to different characteristic marks.

6. The low-altitude UAV environment monitoring and pollution early warning system according to claim 1 is characterized in that: The regional analysis and warning terminal, for the confirmed single abnormal circular area, confirms the abnormal values ​​associated with several spatial points in this abnormal circular area, and averages the confirmed several groups of abnormal values, locks the verification mean, and if the verification mean is greater than Y2, generates a regional warning signal for this abnormal circular area and displays it through the display terminal, where Y2 is a preset value. If the verification mean is ≤Y2, no signal is generated, and the abnormal circular area can be directly displayed through the display terminal.

7. The low-altitude UAV environment monitoring and pollution early warning system according to claim 1 is characterized in that: The regional analysis and warning terminal, for a set of circular areas with the same characteristics, confirms the abnormal values ​​associated with several spatial points of several abnormal circular areas in the set, and performs mean processing on several groups of abnormal values ​​to determine the verification mean. If the verification mean is greater than Y2, a regional warning signal for this set of circular areas with the same characteristics is generated and displayed through the display terminal, where Y2 is a preset value. If the verification mean is ≤Y2, no signal is generated, and several abnormal circular areas in the set of circular areas with the same characteristics can be directly displayed through the display terminal.

Images